Projects
Open source projects and research platforms.
OpenR
β 1,836Open-source framework for advanced LLM reasoning via process reward models, tree search, and reinforcement learning.
SMARTS
β 1,112π Best System Paper, CoRL 2020
Scalable multi-agent RL training school for autonomous driving. Powered NeurIPS 2022 driving challenge.
MALib
β 550JMLR 2023
Parallel framework for population-based multi-agent RL. Supports self-play, league training, and PSRO.
MAT (Multi-Agent Transformer)
β 489NeurIPS 2022
Casting multi-agent RL as a sequence modeling problem. SOTA on cooperative benchmarks. Deployed in real-world multi-AGV warehouse systems.
ZSC-Eval
β 55NeurIPS 2024
Evaluation toolkit and benchmark for multi-agent zero-shot coordination.
GEAR
β 19ICML 2023
GPU-centric experience replay system for large RL models. 6Γ throughput over DeepMind Reverb.
Voice Memo Sync
β 6Intelligently sync, transcribe, and organize Apple Voice Memos with AI. OpenClaw Skill.